{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:08:06Z","timestamp":1789031286143,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374318","type":"print"},{"value":"9783032374325","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37432-5_3","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:24:57Z","timestamp":1789028697000},"page":"38-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5449-9095","authenticated-orcid":false,"given":"Ziyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2823-3901","authenticated-orcid":false,"given":"Siming","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0622-1275","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1829-2826","authenticated-orcid":false,"given":"Shusong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1175-5918","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7817-0665","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8264-6849","authenticated-orcid":false,"given":"Changqing","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1786-4943","authenticated-orcid":false,"given":"Peng-Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"3_CR1","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466 (2023)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Bodur, R., Gundogdu, E., Bhattarai, B., Kim, T.K., Donoser, M., Bazzani, L.: iedit: localised text-guided image editing with weak supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7426\u20137435 (2024)","DOI":"10.1109\/CVPRW63382.2024.00738"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: Masactrl: tuning-free mutual self-attention control for consistent image synthesis and editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22560\u201322570 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"4","key":"3_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graph. (TOG) 42(4), 1\u201310 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H.J., Hui, K.M., Wang, S.Y., Tsao, L.W., Shuai, H.H., Cheng, W.H.: Beautyglow: on-demand makeup transfer framework with reversible generative network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10042\u201310050 (2019)","DOI":"10.1109\/CVPR.2019.01028"},{"key":"3_CR7","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Dit4edit: diffusion transformer for image editing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 2969\u20132977 (2025)","DOI":"10.1609\/aaai.v39i3.32304"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gu, Q., Wang, G., Chiu, M.T., Tai, Y.W., Tang, C.K.: LADN: local adversarial disentangling network for facial makeup and de-makeup. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10481\u201310490 (2019)","DOI":"10.1109\/ICCV.2019.01058"},{"key":"3_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1007\/978-3-030-58529-7_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Guo","year":"2020","unstructured":"Guo, J., Zhu, X., Yang, Y., Yang, F., Lei, Z., Li, S.Z.: Towards fast, accurate and stable 3D dense face alignment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 152\u2013168. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_10"},{"key":"3_CR11","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Hou, C., Wei, G., Chen, Z.: High-fidelity diffusion-based image editing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 2184\u20132192 (2024)","DOI":"10.1609\/aaai.v38i3.27991"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Diffusion model-based image editing: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3541625"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Y., et\u00a0al.: Smartedit: exploring complex instruction-based image editing with multimodal large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8362\u20138371 (2024)","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"3_CR15","unstructured":"Hurst, A., et al.: Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, W., et al.: Psgan: pose and expression robust spatial-aware gan for customizable makeup transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5194\u20135202 (2020)","DOI":"10.1109\/CVPR42600.2020.00524"},{"key":"3_CR17","unstructured":"Kartynnik, Y., Ablavatski, A., Grishchenko, I., Grundmann, M.: Real-time facial surface geometry from monocular video on mobile gpus. arXiv preprint arXiv:1907.06724 (2019)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Kim, M., Jain, A.K., Liu, X.: Adaface: quality adaptive margin for face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18750\u201318759 (2022)","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Kim, M., Su, Y., Liu, F., Jain, A., Liu, X.: Keypoint relative position encoding for face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 244\u2013255 (2024)","DOI":"10.1109\/CVPR52733.2024.00031"},{"key":"3_CR20","unstructured":"Labs, B.F., et\u00a0al.: Flux. 1 kontext: flow matching for in-context image generation and editing in latent space. arXiv preprint arXiv:2506.15742 (2025)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Li, P., Huang, Q., Ding, Y., Li, Z.: Layerdiffusion: layered controlled image editing with diffusion models. In: SIGGRAPH Asia 2023 Technical Communications, pp.\u00a01\u20134. ACM (2023)","DOI":"10.1145\/3610543.3626172"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Li, T., et al.: Beautygan: instance-level facial makeup transfer with deep generative adversarial network. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 645\u2013653 (2018)","DOI":"10.1145\/3240508.3240618"},{"issue":"11","key":"3_CR23","doi-asserted-by":"publisher","first-page":"8538","DOI":"10.1109\/TPAMI.2021.3083484","volume":"44","author":"S Liu","year":"2021","unstructured":"Liu, S., et al.: Psgan++: robust detail-preserving makeup transfer and removal. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 8538\u20138551 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Lu, Q., Yang, X., Taketomi, T.: Beautybank: encoding facial makeup in latent space. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4183\u20134193. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00411"},{"key":"3_CR25","unstructured":"Mou, C., Wang, X., Song, J., Shan, Y., Zhang, J.: Dragondiffusion: enabling drag-style manipulation on diffusion models. arXiv preprint arXiv:2307.02421 (2023)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Nguyen, T., Tran, A.T., Hoai, M.: Lipstick ain\u2019t enough: beyond color matching for in-the-wild makeup transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13305\u201313314 (2021)","DOI":"10.1109\/CVPR46437.2021.01310"},{"key":"3_CR27","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"3_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"3_CR29","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents, 1(2), 3 (2022). arXiv preprint arXiv:2204.06125"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Ruan, B.K., Shuai, H.H.: Mad: makeup all-in-one with cross-domain diffusion model. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 749\u2013758 (2025)","DOI":"10.1109\/CVPRW67362.2025.00079"},{"key":"3_CR32","doi-asserted-by":"publisher","first-page":"36479","DOI":"10.52202\/068431-2643","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Sun, Y., Yu, L., Xie, H., Li, J., Zhang, Y.: Diffam: diffusion-based adversarial makeup transfer for facial privacy protection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24584\u201324594 (2024)","DOI":"10.1109\/CVPR52733.2024.02321"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Sun, Z., Chen, Y., Xiong, S.: Ssat: a symmetric semantic-aware transformer network for makeup transfer and removal. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 2325\u20132334 (2022)","DOI":"10.1609\/aaai.v36i2.20131"},{"key":"3_CR35","doi-asserted-by":"publisher","first-page":"16016","DOI":"10.52202\/079017-0510","volume":"37","author":"Z Sun","year":"2024","unstructured":"Sun, Z., Xiong, S., Chen, Y., Du, F., Chen, W., Wang, F., Rong, Y.: Shmt: self-supervised hierarchical makeup transfer via latent diffusion models. Adv. Neural. Inf. Process. Syst. 37, 16016\u201316042 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Sun, Z., Xiong, S., Chen, Y., Rong, Y.: Content-style decoupling for unsupervised makeup transfer without generating pseudo ground truth. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7601\u20137610 (2024)","DOI":"10.1109\/CVPR52733.2024.00726"},{"key":"3_CR37","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"3_CR38","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"3_CR39","doi-asserted-by":"publisher","unstructured":"Xiang, J., Chen, J., Liu, W., Hou, X., Shen, L.: Ramgan: region attentive morphing gan for region-level makeup transfer. In: European Conference on Computer Vision, pp. 719\u2013735. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_41","DOI":"10.1007\/978-3-031-20047-2_41"},{"key":"3_CR40","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Yan, Q., Guo, C., Zhao, J., Dai, Y., Loy, C.C., Li, C.: Beautyrec: robust, efficient, and component-specific makeup transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1102\u20131110 (2023)","DOI":"10.1109\/CVPRW59228.2023.00117"},{"key":"3_CR42","doi-asserted-by":"publisher","unstructured":"Yang, C., He, W., Xu, Y., Gao, Y.: Elegant: exquisite and locally editable gan for makeup transfer. In: European Conference on Computer Vision, pp. 737\u2013754. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19787-1_42","DOI":"10.1007\/978-3-031-19787-1_42"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: 3d-scenedreamer: text-driven 3d-consistent scene generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10170\u201310180 (2024)","DOI":"10.1109\/CVPR52733.2024.00969"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yuan, Y., Song, Y., Liu, J.: Stablemakeup: when real-world makeup transfer meets diffusion model. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u20139 (2025)","DOI":"10.1145\/3721238.3730702"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, J., Lu, Y., Yang, Z., Yang, Y.: In-context edit: enabling instructional image editing with in-context generation in large scale diffusion transformer. arXiv preprint arXiv:2504.20690 (2025)","DOI":"10.52202\/085713-4646"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, L., Ghosh, A., Metaxas, D.N., Ren, J.: Sine: single image editing with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6027\u20136037 (2023)","DOI":"10.1109\/CVPR52729.2023.00584"},{"issue":"8","key":"3_CR47","doi-asserted-by":"publisher","first-page":"3062","DOI":"10.1109\/TCSVT.2020.3037688","volume":"31","author":"Y Zhao","year":"2020","unstructured":"Zhao, Y., Po, L.M., Cheung, K.W., Yu, W.Y., Rehman, Y.A.U.: Scgan: saliency map-guided colorization with generative adversarial network. IEEE Trans. Circuits Syst. Video Technol. 31(8), 3062\u20133077 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3_CR48","unstructured":"Zhu, J., et\u00a0al.: Flux-makeup: high-fidelity, identity-consistent, and robust makeup transfer via diffusion transformer. arXiv preprint arXiv:2508.05069 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37432-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:25:13Z","timestamp":1789028713000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37432-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374318","9783032374325"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37432-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}